arXiv:2605.06642v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly used as interactive agents, but optimizing them for long-horizon decision making remains difficult because current methods are largely purely reactive, which…
arXiv:2605.05957v1 Announce Type: new
Abstract: LLMs reliably correct false claims when presented in isolation, yet when the same claims are embedded in task-oriented requests, they often comply rather than correct. We term this failure mode \emph{cor…
arXiv:2605.06667v1 Announce Type: cross
Abstract: For artistic applications, video generation requires fine-grained control over both performance and cinematography, i.e., the actor’s motion and the camera trajectory. We present ActCam, a zero-shot me…
arXiv:2510.19316v2 Announce Type: replace
Abstract: Large Multimodal Models encode extensive factual knowledge in their pre-trained weights. However, its knowledge remains static and limited, unable to keep pace with real-world developments, which hin…
arXiv:2605.06130v1 Announce Type: new
Abstract: A persistent skill library allows language model agents to reuse successful strategies across tasks. Maintaining such a library requires three coupled capabilities. The agent selects a relevant skill, ut…
arXiv:2605.06407v1 Announce Type: cross
Abstract: Integrating speech understanding and generation is a pivotal step toward building unified speech models. However, the different representations required for these two tasks currently pose significant c…
arXiv:2605.06472v1 Announce Type: new
Abstract: LLM-based workflows compose specialized agents to execute complex tasks, and these agents usually share substantial context, allowing KV-Cache reuse to save computation. Existing approaches either manage…
A LinkedIn feature that allows paid subscribers to view a list of visitors to their profile should be made available to all EU users free of charge to comply with the region’s General Data Protection Regulation (GDPR), a legal co…
arXiv:2605.03546v1 Announce Type: cross
Abstract: Turning ideas into full software projects from scratch has become a popular use case for language models. Agents are being deployed to seed, maintain, and grow codebases over extended periods with mini…
arXiv:2605.03929v2 Announce Type: cross
Abstract: Stem retrieval, the task of matching missing stems to a given audio submix, is a key challenge currently limited by models that discard temporal information. We introduce PHALAR, a contrastive framewor…